Change locations inside a phone video with AI

Step by step

Run the workflow

1. 01

   The full workflow behind how I made this exact video

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Follow the shown setup, keep the source order unchanged, and run one controlled test.

   

   

   

   

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
2. 02

   Prepare the source material

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Record videos of yourself acting the scenes out

   

   

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
3. 03

   Generate the source images

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Screen shot the keyframes from your recorded footage and drop the reference images into ChatGPT with my prompt (Next Page).
   2. These are the screenshots from my video

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
4. 04

   Overall Preview

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Maintain the same chat for all the image generation that belongs to the same scenes (Next page for page by page breakdown):

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
5. 05

   Generate the next reference image 1

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
   2. Attach the source assets in the same order described by the prompt, then run one controlled test.

   Working asset

   Do the image generation all inside the same chat thread inside your ChatGPT.
   
   Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. Remove the selfie stick. He is sitting at his table looking at his phone, waiting for his pancake. And this is a pov of the waiter holding the pancake walking towards him. Do not change the man face, do not change the framing of the camera.

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
6. 06

   Generate the next reference image 2

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
   2. Attach the source assets in the same order described by the prompt, then run one controlled test.

   Working asset

   Do the image generation all inside the same chat thread inside your ChatGPT.
   
   Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. Remove the selfie stick. He is sitting at his table putting down his phone and in front of him is the plate of pancake that he got served. Do not change the man face, do not change the framing of the camera.

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
7. 07

   Generate the next reference image 3

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
   2. Attach the source assets in the same order described by the prompt, then run one controlled test.

   Working asset

   Do the image generation all inside the same chat thread inside your ChatGPT.
   
   Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. The camera framing is a profile shot from the left. He is sitting at his table, reaching a utensil with his left hand and ready to eat the pancake that he got served. Do not change the man's face, do not change the framing of the camera.

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
8. 08

   Generate the next reference image 4

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
   2. Attach the source assets in the same order described by the prompt, then run one controlled test.

   Working asset

   Do the image generation all inside the same chat thread inside your ChatGPT.
   
   Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. The camera framing is a profile shot from the left. He is sitting at his table, taking a bite of the pancake that he was served. Do not change the man's face, do not change the framing of the camera.

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
9. 09

   Generate the next reference image 5

   Use the source inputs to complete this stage and produce a result that can be checked before continuing.

   1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
   2. Attach the source assets in the same order described by the prompt, then run one controlled test.

   Working asset

   Do the image generation all inside the same chat thread inside your ChatGPT.
   
   Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. Remove the selfie stick; his left hand is holding a utensil instead, and he is sitting up straight instead of leaning forward. The camera ultra wide framing, frontal angle, slightly tilted. He is sitting at his table, chewing on the pancake, the pancake was already sliced as per previous image. Do not change the man's face, do not change the framing of the camera.

   

   Common failure modes

   • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
   • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
10. 10

    Generate the next reference image 6

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
    2. Attach the source assets in the same order described by the prompt, then run one controlled test.

    Working asset

    Do the image generation all inside the same chat thread inside your ChatGPT.
    
    Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. His both hand are on his head in shock because the pancake is so good. The camera ultra wide framing but is close up framing on his face, at a frontal angle. Do not change the man's face, do not change the framing of the camera.

    

    Common failure modes

    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
11. 11

    Generate the next reference image 7

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Copy the prompt below and replace any project-specific subject, product, location, or format details.
    2. Attach the source assets in the same order described by the prompt, then run one controlled test.

    Working asset

    Do the image generation all inside the same chat thread inside your ChatGPT.
    
    Generate an image of changing the location of this man to be at an American roadside diner from the late 1970s. Remove the selfie stick; The camera side angle from slightly higher framing. He is sitting at his table with the pancake already sliced as per the previous image. He opened his mouth as if he were shouting. Do not change the man's face, do not change the framing of the camera.

    

    Common failure modes

    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
12. 12

    Open the video editor

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    • Click here to open Higgsfield (opens in a new tab)Direct link supplied in the source. Source page 14.

    1. With your assets ready, it's time to edit your footages!
    2. I am using Higgsfield for my Seedance 2.0:

    

    

    

    

    

    

    

    

    

    Common failure modes

    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
13. 13

    Set the edit rhythm

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Raw AI footage is your base. Post-production is where it becomes cinematic.
    2. Temporal Remapping (Speed Ramps):
    3. Use speed curves to create rhythm and emphasize key moments.

    

    

    

    Common failure modes

    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
14. 14

    Grade the colour

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Visual Enhancement: Glow
    2. Apply a "Soft Glow" or "Edge Glow" effect to simulate high-end lens diffusion and luxury aesthetics.
    3. Color Grading: The Final Look
    4. Final color adjustments allow you to refine the mood beyond the AI's base

    

    

    

    

    

    Common failure modes

    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
15. 15

    Polish and export the final edit

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    • Click here to open CapCut (opens in a new tab)Direct link supplied in the source. The Workflow Lab may earn a commission. Source page 21.

    1. Polish is what makes it feel expensive. Fine-tuning is what maximizes impact and gives your commercial a premium finish.

    

    Common failure modes

    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.

Before you use it

Final checks

• Check the full result for changed people, products, text, timing, or layout.
• Confirm the tool, model, controls, and cost before generating.
• Keep private or unreleased material out of third-party tools.